ContactOpt: Optimizing Contact to Improve Grasps
Not on the map. Why?
Abstract (arXiv)
Physical contact between hands and objects plays a critical role in human grasps. We show that optimizing the pose of a hand to achieve expected contact with an object can improve hand poses inferred via image-based methods. Given a hand mesh and an object mesh, a deep model trained on ground truth contact data infers desirable contact across the surfaces of the meshes. Then, ContactOpt efficiently optimizes the pose of the hand to achieve desirable contact using a differentiable contact model. Notably, our contact model encourages mesh interpenetration to approximate deformable soft tissue in the hand. In our evaluations, our methods result in grasps that better match ground truth contact, have lower kinematic error, and are significantly preferred by human participants. Code and models are available online.
Key facts. Cited by 137 papers in the map (data through 7 Oct 2026). Builds on 32 of its 61 references that are in the map. First posted on arXiv 15 Apr 2021.
Builds on
32 of 61 references.
References · 32
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
- 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,061
- 2018Learning Dexterous In-Hand Manipulationcited by 643
- 2020GRAB: A Dataset of Whole-Body Human Grasping of Objectscited by 397
- 2019Learning joint reconstruction of hands and manipulated objectscited by 377
- 2019FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Imagescited by 271
- 2017Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metricscited by 259
- 2017First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotationscited by 229
- 2015Supersizing Self-supervision: Learning to Grasp from 50K Tries and 700 Robot Hourscited by 208
- 2020ContactPose: A Dataset of Grasps with Object Contact and Hand Posecited by 180
20 more
- 2020Grasping Field: Learning Implicit Representations for Human Graspscited by 178
- 2017GANerated Hands for Real-time 3D Hand Tracking from Monocular RGBcited by 147
- 2019ContactDB: Analyzing and Predicting Grasp Contact via Thermal Imagingcited by 145
- 2019H+O: Unified Egocentric Recognition of 3D Hand-Object Poses and Interactionscited by 139
- 2020Leveraging Photometric Consistency over Time for Sparsely Supervised Hand-Object Reconstructioncited by 139
- 2020Combining Implicit Function Learning and Parametric Models for 3D Human Reconstructioncited by 133
- 2019Generating 3D People in Scenes without Peoplecited by 127
- 2018Closing the Loop for Robotic Grasping: A Real-time, Generative Grasp Synthesis Approachcited by 117
- 2015Capturing Hands in Action using Discriminative Salient Points and Physics Simulationcited by 115
- 2020HOPE-Net: A Graph-based Model for Hand-Object Pose Estimationcited by 112
- 2020Weakly Supervised 3D Hand Pose Estimation via Biomechanical Constraintscited by 97
- 2020Contact and Human Dynamics from Monocular Videocited by 94
- 2019ContactGrasp: Functional Multi-finger Grasp Synthesis from Contactcited by 87
- 2018Jacquard: A Large Scale Dataset for Robotic Grasp Detectioncited by 86
- 2017Real-time Hand Tracking under Occlusion from an Egocentric RGB-D Sensorcited by 84
- 2016Real-time Joint Tracking of a Hand Manipulating an Object from RGB-D Inputcited by 56
- 2017BigHand2.2M Benchmark: Hand Pose Dataset and State of the Art Analysiscited by 46
- 2020Detecting Hands and Recognizing Physical Contact in the Wildcited by 38
- 2020Bodies at Rest: 3D Human Pose and Shape Estimation from a Pressure Image using Synthetic Datacited by 34
- 2015Illusory Sense of Human Touch from a Warm and Soft Artificial Handcited by 1
Built on by
Citing papers per year: 2021: 7; 2022: 16; 2023: 35; 2024: 32; 2025: 24; 2026: 23.
137 papers.
Sort:
By area:
- 2022ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulationcited by 306
- 2022BEHAVE: Dataset and Method for Tracking Human Object Interactionscited by 246
- 2023InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusioncited by 181
- 2021GOAL: Generating 4D Whole-Body Motion for Hand-Object Graspingcited by 142
- 2023CG-HOI: Contact-Guided 3D Human-Object Interaction Generationcited by 137
- 2022OakInk: A Large-scale Knowledge Repository for Understanding Hand-Object Interactioncited by 129
- 2022IMos: Intent-Driven Full-Body Motion Synthesis for Human-Object Interactionscited by 121
- 2023UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policycited by 117
- 2023Affordance Diffusion: Synthesizing Hand-Object Interactionscited by 110
- 2021D-Grasp: Physically Plausible Dynamic Grasp Synthesis for Hand-Object Interactionscited by 109
- 2022What's in your hands? 3D Reconstruction of Generic Objects in Handscited by 90
- 2021SAGA: Stochastic Whole-Body Grasping with Contactcited by 89
38 more
- 2023Hi4D: 4D Instance Segmentation of Close Human Interactioncited by 87
- 2024Text2HOI: Text-guided 3D Motion Generation for Hand-Object Interactioncited by 84
- 2021ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesiscited by 76
- 2023HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Videocited by 76
- 2022TOCH: Spatio-Temporal Object-to-Hand Correspondence for Motion Refinementcited by 69
- 2024Human-Object Interaction from Human-Level Instructionscited by 62
- 2022GenDexGrasp: Generalizable Dexterous Graspingcited by 54
- 2023DECO: Dense Estimation of 3D Human-Scene Contact In The Wildcited by 54
- 2023ArtiGrasp: Physically Plausible Synthesis of Bi-Manual Dexterous Grasping and Articulationcited by 53
- 2024ReGenNet: Towards Human Action-Reaction Synthesiscited by 53
- 2023Physically Plausible Full-Body Hand-Object Interaction Synthesiscited by 52
- 2023ContactGen: Generative Contact Modeling for Grasp Generationcited by 52
- 2021A Skeleton-Driven Neural Occupancy Representation for Articulated Handscited by 50
- 2022FLEX: Full-Body Grasping Without Full-Body Graspscited by 46
- 2024G-HOP: Generative Hand-Object Prior for Interaction Reconstruction and Grasp Synthesiscited by 43
- 2023Detecting Human-Object Contact in Imagescited by 41
- 2023Task-Oriented Human-Object Interactions Generation with Implicit Neural Representationscited by 41
- 2024HOIDiffusion: Generating Realistic 3D Hand-Object Interaction Datacited by 37
- 2023Object pop-up: Can we infer 3D objects and their poses from human interactions alone?cited by 36
- 2023Dexterous Functional Graspingcited by 36
- 2024Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with Objectscited by 35
- 2022Learning Continuous Grasping Function with a Dexterous Hand from Human Demonstrationscited by 34
- 2024GeneOH Diffusion: Towards Generalizable Hand-Object Interaction Denoising via Denoising Diffusioncited by 33
- 2024EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wildcited by 33
- 2024Beyond the Contact: Discovering Comprehensive Affordance for 3D Objects from Pre-trained 2D Diffusion Modelscited by 32
- 2023UGG: Unified Generative Graspingcited by 30
- 2024SemGrasp: Semantic Grasp Generation via Language Aligned Discretizationcited by 29
- 2024InterHandGen: Two-Hand Interaction Generation via Cascaded Reverse Diffusioncited by 28
- 2023GRIP: Generating Interaction Poses Using Spatial Cues and Latent Consistencycited by 26
- 2025A Survey on Human Interaction Motion Generationcited by 25
- 2022PressureVision: Estimating Hand Pressure from a Single RGB Imagecited by 23
- 2025PICO: Reconstructing 3D People In Contact with Objectscited by 22
- 2022Contact2Grasp: 3D Grasp Synthesis via Hand-Object Contact Constraintcited by 21
- 2024ManiDext: Hand-Object Manipulation Synthesis via Continuous Correspondence Embeddings and Residual-Guided Diffusioncited by 21
- 2021BodyPressure -- Inferring Body Pose and Contact Pressure from a Depth Imagecited by 20
- 2024GEARS: Local Geometry-aware Hand-object Interaction Synthesiscited by 20
- 2022Physical Interaction: Reconstructing Hand-object Interactions with Physicscited by 19
- 2023Grasp Multiple Objects with One Handcited by 18
50 most cited of 137 All 137 (JSON)
- 2026EgoFound3R: End-to-End Egocentric Hand Reconstruction in World Space with Point-Wise Interaction Attributes1 Oct 2026
- 2026DynamicHOI: Coupled Dynamics for Physics-aware HOI Reconstruction29 Sep 2026
- 2026ConGraspXL: Controllable Constraint-Conditioned Dexterous Grasping Motion Synthesis14 Sep 2026
- 2026EgoTac: In-the-wild Tactile Prediction from Egocentric Vision15 Aug 2026
- 2026HOPE: Hand-Object Pressure Estimation from Monocular Videos6 Aug 2026
- 2026Hand-Object Interaction in the Age of Large Foundation Models:Reconstruction, Generation, and Embodied Transfer30 Jul 2026
- 2026ContactFlow: A video action conditioning that transfers across embodiments29 Jul 2026
- 2026JointHOI: Jointly Generating Contact Maps Enhances Hand Object Interaction Generation2 Jul 2026
- 2026Towards in-the-wild Egocentric 3D Hand-Object Pose Estimation29 Jun 2026
- 2026DCGrasp: Distance-aware Controllable Grasp Generation29 Jun 2026
- 2026MOCHI: Motion Enhancement of Collaborative Human-object Interactions16 Jun 2026
- 2026V2P-Manip: Learning Dexterous Manipulation from Monocular Human Videos15 Jun 2026
38 more
- 2026NDPP-Grasp: Non-Differentiable Physical Plausibility Constraint-Guided Task-Oriented Dexterous Grasp Generation1 Jun 2026
- 2026GeoHand: Unlocking Prior Geometry Knowledge for Monocular 3D Hand Reconstruction17 May 2026
- 2026PhysHanDI: Physics-Based Reconstruction of Hand-Deformable Object Interactions10 May 2026
- 2026LEXIS: LatEnt ProXimal Interaction Signatures for 3D HOI from an Image22 Apr 2026
- 2026ArtHOI: Taming Foundation Models for Monocular 4D Reconstruction of Hand-Articulated-Object Interactions26 Mar 2026
- 2026DuetHOI: Language-Guided Bimanual Hand--Object Motion Generation with Articulation Planning and Contact Refinement9 Mar 2026
- 2026FlowHOI: Flow-based Semantics-Grounded Generation of Hand-Object Interactions for Dexterous Robot Manipulation13 Feb 2026
- 2026Dexterous Manipulation Policies from RGB Human Videos via 3D Hand-Object Trajectory Reconstruction9 Feb 2026
- 2026Grasp-and-Lift: Executable 3D Hand-Object Interaction Reconstruction via Physics-in-the-Loop Optimization26 Jan 2026
- 2026Copy-Trasform-Paste: Zero-Shot Object-Object Alignment Guided by Vision-Language and Geometric Constraints20 Jan 2026
- 2026EgoGrasp: World-Space Hand-Object Interaction Estimation from Egocentric Videos3 Jan 2026
- 2025AnchorHOI: Zero-shot Generation of 4D Human-Object Interaction via Anchor-based Prior Distillation16 Dec 2025
- 2025Open-world Hand-Object Interaction Video Generation Based on Structure and Contact-aware Representation1 Dec 2025
- 2025VPHO: Joint Visual-Physical Cue Learning and Aggregation for Hand-Object Pose Estimation15 Nov 2025
- 2025Contact Map Transfer with Conditional Diffusion Model for Generalizable Dexterous Grasp Generation3 Nov 2025
- 2025SynHLMA:Synthesizing Hand Language Manipulation for Articulated Object with Discrete Human Object Interaction Representation29 Oct 2025
- 2025MOGRAS: Human Motion with Grasping in 3D Scenes25 Oct 2025
- 2025Advances in 4D Representation: Geometry, Motion, and Interaction22 Oct 2025
- 2025CEDex: Cross-Embodiment Dexterous Grasp Generation at Scale from Human-like Contact Representations29 Sep 2025
- 2025Generative Modeling of Shape-Dependent Self-Contact Human Poses27 Sep 2025
- 2025Follow My Hold: Hand-Object Interaction Reconstruction through Geometric Guidance25 Aug 2025
- 2025MagicHOI: Leveraging 3D Priors for Accurate Hand-object Reconstruction from Short Monocular Video Clips7 Aug 2025
- 2025Task-Oriented Human Grasp Synthesis via Context- and Task-Aware Diffusers15 Jul 2025
- 2025Towards Dynamic 3D Reconstruction of Hand-Instrument Interaction in Ophthalmic Surgery23 May 2025
- 2025Learning Dense Hand Contact Estimation from Imbalanced Data16 May 2025
- 2025GRACE: Estimating Geometry-level 3D Human-Scene Contact from 2D Images10 May 2025
- 2025Web2Grasp: Learning Functional Grasps from Web Images of Hand-Object Interactions7 May 2025
- 2025PartHOI: Part-based Hand-Object Interaction Transfer via Generalized Cylinders29 Apr 2025
- 2025PICO: Reconstructing 3D People In Contact with Objects24 Apr 2025
- 2025ZeroGrasp: Zero-Shot Shape Reconstruction Enabled Robotic Grasping15 Apr 2025
- 2025Zero-Shot Human-Object Interaction Synthesis with Multimodal Priors25 Mar 2025
- 2025G-DexGrasp: Generalizable Dexterous Grasping Synthesis Via Part-Aware Prior Retrieval and Prior-Assisted Generation25 Mar 2025
- 2025A Survey on Human Interaction Motion Generation17 Mar 2025
- 2025FunHOI: Annotation-Free 3D Hand-Object Interaction Generation via Functional Text Guidance28 Feb 2025
- 2025AnyDexGrasp: General Dexterous Grasping for Different Hands with Human-level Learning Efficiency23 Feb 2025
- 2024ManiVideo: Generating Hand-Object Manipulation Video with Dexterous and Generalizable Grasping18 Dec 2024
- 2024TriDi: Trilateral Diffusion of 3D Humans, Objects, and Interactions9 Dec 2024
- 2024FIction: 4D Future Interaction Prediction from Video1 Dec 2024
50 newest of 137 All 137 (JSON)
- 2023Affordance Diffusion: Synthesizing Hand-Object Interactionscited by 110
- 2024G-HOP: Generative Hand-Object Prior for Interaction Reconstruction and Grasp Synthesiscited by 43
- 2024HOIDiffusion: Generating Realistic 3D Hand-Object Interaction Datacited by 37
- 2024GeneOH Diffusion: Towards Generalizable Hand-Object Interaction Denoising via Denoising Diffusioncited by 33
- 2024Beyond the Contact: Discovering Comprehensive Affordance for 3D Objects from Pre-trained 2D Diffusion Modelscited by 32
- 2024InterHandGen: Two-Hand Interaction Generation via Cascaded Reverse Diffusioncited by 28
- 2024ManiDext: Hand-Object Manipulation Synthesis via Continuous Correspondence Embeddings and Residual-Guided Diffusioncited by 21
- 2025MagicHOI: Leveraging 3D Priors for Accurate Hand-object Reconstruction from Short Monocular Video Clipscited by 15
- 2024NL2Contact: Natural Language Guided 3D Hand-Object Contact Modeling with Diffusion Modelcited by 10
- 2025Follow My Hold: Hand-Object Interaction Reconstruction through Geometric Guidancecited by 8
- 2024FastGrasp: Efficient Grasp Synthesis with Diffusioncited by 7
- 2026EgoGrasp: World-Space Hand-Object Interaction Estimation from Egocentric Videoscited by 7
12 most cited of 16 All 16 (JSON)
- 2026NDPP-Grasp: Non-Differentiable Physical Plausibility Constraint-Guided Task-Oriented Dexterous Grasp Generation1 Jun 2026
- 2026EgoGrasp: World-Space Hand-Object Interaction Estimation from Egocentric Videos3 Jan 2026
- 2025AnchorHOI: Zero-shot Generation of 4D Human-Object Interaction via Anchor-based Prior Distillation16 Dec 2025
- 2025Contact Map Transfer with Conditional Diffusion Model for Generalizable Dexterous Grasp Generation3 Nov 2025
- 2025Follow My Hold: Hand-Object Interaction Reconstruction through Geometric Guidance25 Aug 2025
- 2025MagicHOI: Leveraging 3D Priors for Accurate Hand-object Reconstruction from Short Monocular Video Clips7 Aug 2025
- 2024FastGrasp: Efficient Grasp Synthesis with Diffusion22 Nov 2024
- 2024ManiDext: Hand-Object Manipulation Synthesis via Continuous Correspondence Embeddings and Residual-Guided Diffusion14 Sep 2024
- 2024NL2Contact: Natural Language Guided 3D Hand-Object Contact Modeling with Diffusion Model17 Jul 2024
- 2024G-HOP: Generative Hand-Object Prior for Interaction Reconstruction and Grasp Synthesis18 Apr 2024
- 2024InterHandGen: Two-Hand Interaction Generation via Cascaded Reverse Diffusion26 Mar 2024
- 2024HOIDiffusion: Generating Realistic 3D Hand-Object Interaction Data18 Mar 2024
12 newest of 16 All 16 (JSON)
- 2022ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulationcited by 306
- 2022BEHAVE: Dataset and Method for Tracking Human Object Interactionscited by 246
- 2023InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusioncited by 181
- 2021GOAL: Generating 4D Whole-Body Motion for Hand-Object Graspingcited by 142
- 2023CG-HOI: Contact-Guided 3D Human-Object Interaction Generationcited by 137
- 2022OakInk: A Large-scale Knowledge Repository for Understanding Hand-Object Interactioncited by 129
- 2022IMos: Intent-Driven Full-Body Motion Synthesis for Human-Object Interactionscited by 121
- 2023UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policycited by 117
- 2021D-Grasp: Physically Plausible Dynamic Grasp Synthesis for Hand-Object Interactionscited by 109
- 2022What's in your hands? 3D Reconstruction of Generic Objects in Handscited by 90
- 2021SAGA: Stochastic Whole-Body Grasping with Contactcited by 89
- 2023Hi4D: 4D Instance Segmentation of Close Human Interactioncited by 87
12 most cited of 120 All 120 (JSON)
- 2026EgoFound3R: End-to-End Egocentric Hand Reconstruction in World Space with Point-Wise Interaction Attributes1 Oct 2026
- 2026DynamicHOI: Coupled Dynamics for Physics-aware HOI Reconstruction29 Sep 2026
- 2026ConGraspXL: Controllable Constraint-Conditioned Dexterous Grasping Motion Synthesis14 Sep 2026
- 2026EgoTac: In-the-wild Tactile Prediction from Egocentric Vision15 Aug 2026
- 2026HOPE: Hand-Object Pressure Estimation from Monocular Videos6 Aug 2026
- 2026Hand-Object Interaction in the Age of Large Foundation Models:Reconstruction, Generation, and Embodied Transfer30 Jul 2026
- 2026JointHOI: Jointly Generating Contact Maps Enhances Hand Object Interaction Generation2 Jul 2026
- 2026Towards in-the-wild Egocentric 3D Hand-Object Pose Estimation29 Jun 2026
- 2026DCGrasp: Distance-aware Controllable Grasp Generation29 Jun 2026
- 2026MOCHI: Motion Enhancement of Collaborative Human-object Interactions16 Jun 2026
- 2026V2P-Manip: Learning Dexterous Manipulation from Monocular Human Videos15 Jun 2026
- 2026GeoHand: Unlocking Prior Geometry Knowledge for Monocular 3D Hand Reconstruction17 May 2026
12 newest of 120 All 120 (JSON)